Chompa1422 commited on
Commit
cd48fb0
·
verified ·
1 Parent(s): 5ea51be

docs: add validated DGX evidence cards

Browse files
.gitattributes CHANGED
@@ -1,3 +1,5 @@
1
  *.safetensors filter=lfs diff=lfs merge=lfs -text
2
  model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
3
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
1
  *.safetensors filter=lfs diff=lfs merge=lfs -text
2
  model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
3
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
4
+ assets/dgx-qwen38-performance.png filter=lfs diff=lfs merge=lfs -text
5
+ assets/dgx-qwen38-evidence.png filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -31,6 +31,8 @@ Validated on one NVIDIA DGX Spark with TensorFold:
31
 
32
  These are workload-specific validation results, not a universal model speed or capability claim. Full protocol and limitations are below.
33
 
 
 
34
  ## Provenance
35
 
36
  | Field | Value |
@@ -60,6 +62,8 @@ The script explicitly skips:
60
 
61
  No quantizer is invoked. All 21 output shard sizes match the pinned base checkpoint. Sampled byte hashes matched the base for routed NVFP4 expert payloads, CSF fixed/exception scales and outer scales; sampled target attention tensors differed as expected. This was a sampled integrity check, not an exhaustive hash of all 373,248 routed-expert keys.
62
 
 
 
63
  ## Performance validation
64
 
65
  ### System and runtime
 
31
 
32
  These are workload-specific validation results, not a universal model speed or capability claim. Full protocol and limitations are below.
33
 
34
+ ![DGX Spark fixed validation results](assets/dgx-qwen38-performance.png)
35
+
36
  ## Provenance
37
 
38
  | Field | Value |
 
62
 
63
  No quantizer is invoked. All 21 output shard sizes match the pinned base checkpoint. Sampled byte hashes matched the base for routed NVFP4 expert payloads, CSF fixed/exception scales and outer scales; sampled target attention tensors differed as expected. This was a sampled integrity check, not an exhaustive hash of all 373,248 routed-expert keys.
64
 
65
+ ![Artifact integrity and bounded refusal check](assets/dgx-qwen38-evidence.png)
66
+
67
  ## Performance validation
68
 
69
  ### System and runtime
assets/dgx-qwen38-evidence.png ADDED

Git LFS Details

  • SHA256: 484a4b9617150fa279ab7fde4281af3b2a26083daa7a7bf545b3687569beff22
  • Pointer size: 131 Bytes
  • Size of remote file: 443 kB
assets/dgx-qwen38-performance.png ADDED

Git LFS Details

  • SHA256: f91aac3e46ae016be4d1eb87ec32d884a428dc0b4e6ccadf989b71540bd3648a
  • Pointer size: 131 Bytes
  • Size of remote file: 431 kB